Ice melting method, device and equipment for overhead line system, storage medium and program product

Abstract

The invention relates to an overhead line system ice melting method and device, equipment, a storage medium and a program product. The method comprises the following steps: acquiring an infrared image and point cloud data of an overhead line system, which are acquired at the same time; carrying out image identification on the infrared image, and determining a first icing thickness of the overhead line system; analyzing the point cloud data, and determining a second icing thickness of the contact network; the first icing thickness and the second icing thickness are fused, and the target icing thickness of the contact network is determined; and based on the target icing thickness, determining an ice melting parameter, and sending the ice melting parameter to the control equipment, so that the control equipment executes an overhead line system ice melting operation based on the ice melting parameter. According to the method, the infrared image of the overhead line system and the icing thickness analysis result of the point cloud data are fused, the accuracy of determining the icing thickness of the overhead line system is improved, meanwhile, even if one data source has an error, other data sources can still continue to provide effective information, the robustness of the system is enhanced, and the reliability of the system is improved. Therefore, a reasonable ice melting strategy is formulated based on the accurate icing thickness.

Description

Technical Field

[0001] The present disclosure relates to the technical field of railway overhead contact network, and in particular to an overhead contact network ice melting method, device, equipment, storage medium and program product. Background Art

[0002] The rapid development of electrified railways has provided great convenience for people's daily travel, but the low temperature, rain, snow and freezing weather have brought severe challenges to railway operations. Among them, once the contact network, which is the core component of the electrified railway, is covered with ice, it not only hinders the power supply, resulting in an increased risk of power outages for trains and affecting the normal operation of trains, but also increases the mechanical load of the contact network, increasing the risk of equipment damage, and posing a major hidden danger to the safe operation of the railway.

[0003] In order to ensure the safe operation of the railway, it is necessary to promptly and effectively remove the ice on the contact network. Among various de-icing measures, the electrothermal de-icing method applies current to the contact network and uses the electrothermal effect to melt the ice. It has the advantages of simple operation, fast de-icing speed, and little damage to equipment. However, in order to achieve a good de-icing effect, the thickness of the ice needs to be accurately determined. If the thickness of the ice is not accurately judged, it will not only affect the de-icing efficiency, but may also cause excessive load on the equipment and even cause safety accidents. Therefore, how to accurately determine the thickness of the ice on the contact network in order to formulate a reasonable de-icing plan and ensure that the de-icing process is stable and controllable has become a technical problem that needs to be solved urgently. Summary of the invention

[0004] In order to solve the above technical problems, the present disclosure provides a contact network ice melting method, device, equipment, storage medium and program product.

[0005] A first aspect of an embodiment of the present disclosure provides a method for melting ice in a contact network, the method comprising:

[0006] Acquire infrared images and point cloud data of the contact network collected simultaneously;

[0007] Performing image recognition on the infrared image to determine a first ice coating thickness of the contact network;

[0008] Analyzing the point cloud data to determine a second ice coating thickness of the contact network;

[0009] The first ice coating thickness and the second ice coating thickness are combined to determine a target ice coating thickness of the contact network;

[0010] Determine ice melting parameters based on the target ice coating thickness, and send the ice melting parameters to a control device so that the control device performs an overhead line ice melting operation based on the ice melting parameters.

[0011] A second aspect of an embodiment of the present disclosure provides a contact network ice melting device, the device comprising:

[0012] An acquisition module, used to acquire infrared images and point cloud data of the contact network collected simultaneously;

[0013] An image recognition module, used for performing image recognition on the infrared image to determine a first ice thickness of the contact network;

[0014] A point cloud analysis module, used for analyzing the point cloud data to determine a second ice thickness of the contact network;

[0015] a thickness determination module, configured to fuse the first ice coating thickness and the second ice coating thickness to determine a target ice coating thickness of the contact network;

[0016] The parameter determination module is used to determine ice melting parameters based on the target ice coating thickness, and send the ice melting parameters to the control device, so that the control device performs the contact network ice melting operation based on the ice melting parameters.

[0017] A third aspect of an embodiment of the present disclosure provides a computer device, including a memory and a processor, and a computer program, wherein the computer program is stored in the memory, and when the computer program is executed by the processor, the contact network de-icing method as described in the first aspect above is implemented.

[0018] A fourth aspect of an embodiment of the present disclosure provides a computer-readable storage medium, in which a computer program is stored. When the computer program is executed by a processor, the contact network de-icing method as described in the first aspect above is implemented.

[0019] A fifth aspect of the embodiments of the present disclosure provides a computer program product, including a computer program, which, when executed by a processor, implements the contact network ice melting method as described in the first aspect above.

[0020] Compared with the prior art, the technical solution provided by the embodiments of the present disclosure has the following advantages:

[0021] In the contact network ice melting method, device, equipment, storage medium and program product provided in the embodiments of the present invention, by acquiring the infrared image and point cloud data of the contact network collected at the same time, image recognition is performed on the infrared image to determine the first ice thickness of the contact network, the point cloud data is analyzed to determine the second ice thickness of the contact network, the first ice thickness and the second ice thickness are fused to determine the target ice thickness of the contact network, ice melting parameters are determined based on the target ice thickness, and the ice melting parameters are sent to the control device so that the control device performs the contact network ice melting operation based on the ice melting parameters. The ice thickness analysis results of the infrared image and point cloud data of the contact network can be fused to improve the accuracy of the determination of the ice thickness of the contact network. At the same time, even if an error occurs in a certain data source, other data sources can continue to provide effective information to enhance the robustness of the system, so as to formulate a reasonable ice melting strategy based on the accurate ice thickness to ensure the ice melting effect and ensure that the contact network can operate safely and stably under extreme weather conditions. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the principles of the present disclosure.

[0023] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0024] Figure 1 is a flow chart of a contact network ice melting method provided by an embodiment of the present disclosure;

[0025] Figure 2 is a flow chart of a method for acquiring infrared images and point cloud data provided by an embodiment of the present disclosure;

[0026] Figure 3 is a structural diagram of a monitoring terminal provided by an embodiment of the present disclosure;

[0027] Figure 4 It is a structural schematic diagram of a monitoring terminal fixed on a contact network provided by an embodiment of the present disclosure;

[0028] Figure 5 is a flow chart of a method for determining a second ice thickness provided by an embodiment of the present disclosure;

[0029] Figure 6 is a flow chart of a method for performing an ice melting operation provided by an embodiment of the present disclosure;

[0030] Figure 7It is a structural schematic diagram of a contact network ice melting device provided by an embodiment of the present disclosure;

[0031] Figure 8 It is a structural diagram of a computer device provided in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0032] In order to more clearly understand the above-mentioned objectives, features and advantages of the present disclosure, the scheme of the present disclosure will be further described below. It should be noted that the embodiments of the present disclosure and the features in the embodiments can be combined with each other without conflict.

[0033] In the following description, many specific details are set forth to facilitate a full understanding of the present disclosure, but the present disclosure may also be implemented in other ways different from those described herein; it is obvious that the embodiments in the specification are only part of the embodiments of the present disclosure, rather than all of the embodiments.

[0034] It should be understood that the various steps described in the method embodiments of the present disclosure may be performed in different orders and / or in parallel. In addition, the method embodiments may include additional steps and / or omit the steps shown. The scope of the present disclosure is not limited in this respect.

[0035] Figure 1 The present invention provides a flowchart of a method for melting ice in a contact network, which can be performed by a device for melting ice in a contact network. The device for melting ice in a contact network can be implemented in software and / or hardware. The device for melting ice in a contact network can be configured in an electronic device, such as a server or a terminal, wherein the terminal specifically includes a mobile phone, a computer or a tablet computer, etc. Figure 1 As shown, the contact network de-icing method provided in this embodiment includes the following steps:

[0036] S101, acquiring infrared images and point cloud data of the contact network collected simultaneously.

[0037] In the disclosed embodiment, the contact network ice-melting device can respectively obtain infrared images and point cloud data obtained by the infrared camera and the laser radar when collecting data on the contact network at the same position at the same time.

[0038] In an exemplary implementation of the disclosed embodiment, the contact network ice-melting device can simultaneously send data collection instructions to the infrared camera and the laser radar, so that the infrared camera and the laser radar can simultaneously collect infrared images and point cloud data.

[0039] S102: Perform image recognition on the infrared image to determine a first ice thickness of the contact network.

[0040] In the disclosed embodiment, the contact network ice melting device can perform image recognition processing on the infrared image after acquiring the infrared image of the contact network, and determine the first ice coating thickness of the contact network in the infrared image.

[0041] In an exemplary implementation of the disclosed embodiment, the contact network ice-melting device can pre-process the infrared image after acquiring the infrared image, including denoising processing (such as median filtering, Gaussian filtering) and image enhancement processing (such as histogram equalization), and perform image segmentation on the infrared image according to a preset temperature threshold, determine the ice-covered area and non-ice-covered area in the infrared image, and then determine the actual size corresponding to the ice-covered area according to the calibration parameters of the infrared camera acquired in advance, and determine the first ice thickness of the contact network in combination with the size information of the contact network.

[0042] S103: Analyze the point cloud data to determine the second ice thickness of the contact network.

[0043] In the disclosed embodiment, the contact network ice-melting device may analyze the point cloud data after acquiring the point cloud data of the contact network, and determine the second ice coating thickness of the contact network in the point cloud data.

[0044] In an exemplary implementation of the disclosed embodiment, the contact network de-icing device can analyze the point cloud data after acquiring the point cloud data, determine the ice-covered area and the un-ice-covered area in the point cloud data, and then compare the diameter of the ice-covered area with the diameter of the un-ice-covered area to determine the second ice thickness of the contact network.

[0045] S104: The first ice coating thickness and the second ice coating thickness are integrated to determine a target ice coating thickness of the contact network.

[0046] In the disclosed embodiment, the contact network ice melting device can analyze the infrared image and point cloud data of the contact network respectively to obtain a first ice thickness and a second ice thickness, and then fuse the first ice thickness and the second ice thickness to obtain a fused target ice thickness.

[0047] In an exemplary implementation of the disclosed embodiment, the contact network ice melting device may use a weighted average method to fuse the first ice thickness and the second ice thickness. The specific weights may be pre-set based on experience, or a decision layer fusion may be used to obtain the target ice thickness, which is not limited here.

[0048] S105. Determine ice melting parameters based on the target ice coating thickness, and send the ice melting parameters to the control device, so that the control device performs an overhead contact network ice melting operation based on the ice melting parameters.

[0049] The ice melting parameters in the embodiments of the present disclosure may be understood as control parameters for melting the contact network using an electrothermal-based ice melting method. For example, the ice melting parameters may include the magnitude of the ice melting current and the current duration.

[0050] In the embodiment of the present disclosure, the contact network ice-melting device can determine the ice-melting parameters when performing the contact network ice-melting operation according to the target ice-melting thickness after determining the target ice-melting thickness, and send the ice-melting parameters to the control device, so that the control device can perform the contact network ice-melting operation based on the ice-melting parameters after receiving the ice-melting parameters.

[0051] In an exemplary implementation of the disclosed embodiment, the overhead line ice-melting device may determine the ice-melting parameters corresponding to the target ice-covering thickness according to a preset correspondence between the ice-covering thickness and the ice-melting parameters.

[0052] In another exemplary implementation of the disclosed embodiment, the ice-melting effect based on electrothermal force is also closely related to environmental parameters. The contact network ice-melting device can obtain environmental parameters such as ambient temperature, ambient humidity, ambient wind speed, etc., and then substitute the target ice thickness and environmental parameters into preset thermodynamic formulas to calculate the ice-melting current, and then deduce the current duration based on the ice-melting current.

[0053] The disclosed embodiment acquires infrared images and point cloud data of the contact network collected simultaneously, performs image recognition on the infrared images, determines a first ice thickness of the contact network, analyzes the point cloud data, determines a second ice thickness of the contact network, fuses the first ice thickness with the second ice thickness, determines a target ice thickness of the contact network, determines ice melting parameters based on the target ice thickness, and sends the ice melting parameters to a control device, so that the control device performs ice melting operations on the contact network based on the ice melting parameters. The infrared images and ice thickness analysis results of the point cloud data of the contact network can be fused to improve the accuracy of determining the ice thickness of the contact network. Even if an error occurs in one data source, other data sources can continue to provide effective information, thereby enhancing the robustness of the system, thereby formulating a reasonable ice melting strategy based on the accurate ice thickness, ensuring the ice melting effect, and ensuring that the contact network can operate safely and stably under extreme weather conditions.

[0054] Figure 2 is a flow chart of a method for obtaining infrared images and point cloud data provided by an embodiment of the present disclosure, such as Figure 2 As shown, based on the above embodiment, infrared images and point cloud data can be obtained by the following method.

[0055] S201. Obtain infrared images and point cloud data of the contact network collected by the monitoring terminal. Two hanging holes provided on the monitoring terminal are respectively hung and fixed on the flat arm and the inclined arm of the contact network support.

[0056] The monitoring terminal in the embodiment of the present disclosure can be understood as a terminal device with infrared image acquisition function and point cloud data acquisition function. For example, the contact network ice melting device can be set on the monitoring terminal or at other locations outside the monitoring terminal.

[0057] Figure 3 Schematic diagram of a monitoring terminal provided by an embodiment of the present disclosure. Figure 3 As shown, in order to facilitate the monitoring terminal to be hung on the network at any time, two hanging holes are set on the monitoring terminal to facilitate the monitoring terminal to be fixed on the contact network. The structural design of the monitoring terminal adopts a modular and layered design, and the monitoring terminal can be divided into three layers.

[0058] In order to obtain infrared images and point cloud data of the contact network, the monitoring terminal needs to be equipped with infrared camera sensors and lidar sensors. In order to obtain environmental parameters, the monitoring terminal can be equipped with temperature and humidity sensors, wind cup wind speed sensors, and wind direction sensors. In the electrothermal ice melting, the contact wire and the catenary often have local overheating. Monitoring the current and temperature of the contact wire and the catenary can detect local overheating in time. Therefore, the monitoring terminal uses two sets of open Hall current sensors and platinum resistance sensors. The two sets of sensors can collect the current distribution and temperature distribution of the contact wire and the catenary.

[0059] Preferably, in order to ensure that each component of the monitoring terminal can work normally, a heating component and an internal temperature monitoring component are also provided inside the monitoring terminal. Specifically, a heating interface and two internal temperature sensors can be provided. When the temperature inside the device is too low, the monitoring terminal automatically starts the heating function, thereby ensuring that the monitoring terminal can work normally. In addition, the monitoring terminal requires a low-temperature special starting battery to ensure that the power supply can start quickly at low temperatures and provide a stable power supply for other components of the monitoring terminal. In order to facilitate the disassembly positioning and maintenance of the monitoring terminal, the monitoring terminal needs to be equipped with a GPS locator to facilitate railway workers to quickly locate the monitoring terminal, and the GPS locator can also bear the time recording function. The monitoring terminal is also equipped with 5 LED lights of different colors to indicate the working status of different sensors, so that railway workers can grasp the working status of the monitoring terminal in time. In addition, the communication function of the monitoring terminal is undertaken by the wireless communication module, and the log recording function is undertaken by the memory card. Since the monitoring terminal integrates many sensors, a single finished control board may not meet the sensor function, so the control board adopts the "core board + baseboard" method, the core board adopts the finished board, and the functions that the core board fails to provide are realized on the baseboard.

[0060] In order to facilitate the two sets of platinum resistance sensors and open Hall current sensors to collect the temperature and current values ​​of the contact wire and the load-bearing cable, they are placed outside the monitoring terminal. GPS and antenna are also placed outside the monitoring terminal. Other sensors are placed inside the monitoring terminal or outside the monitoring terminal structure.

[0061] Furthermore, collecting infrared images and point cloud data of the contact network requires ensuring the stability and reliability of the monitoring terminal. For this purpose, the monitoring terminal is suspended and fixed on the flat arm and inclined arm of the contact network support through two hanging holes. Figure 4 Schematic diagram of a monitoring terminal fixed on a contact network according to an embodiment of the present disclosure. Figure 4 As shown in the figure, the flat arm and the oblique arm are connected to the main body of the support to form a stable triangular support structure. The flat arm extends horizontally to provide lateral support; the oblique arm is tilted upward to provide additional stability and wind resistance for the monitoring terminal. When fixing the monitoring terminal, use a hanging rope or a large cable tie through the hanging hole on the monitoring terminal to hang it firmly on the flat arm and the oblique arm. Through this hanging method, the monitoring terminal not only forms a stable connection with the contact network support, but also can be hung immediately. Whether in normal working conditions or in severe weather conditions, the monitoring terminal can remain stable.

[0062] In the disclosed embodiment, the contact network ice-melting device can obtain infrared images and point cloud data collected by a monitoring terminal suspended and fixed on the contact network over a period of time. By way of example, an infrared image sequence and a point cloud data set can be obtained, as well as the first acquisition time of each infrared image in the infrared image sequence and the second acquisition time of each group of point cloud data in the point cloud data set.

[0063] S202, performing time synchronization processing on the infrared image and the point cloud data to obtain the infrared image and point cloud data of the contact network collected simultaneously.

[0064] In the disclosed embodiment, the contact network de-icing device can perform time synchronization processing on the infrared images and point cloud data of the contact network after acquiring the infrared images and point cloud data of the contact network, and screen out at least one infrared image and point cloud data of the contact network collected simultaneously. Specifically, based on the first collection time of each infrared image and the second collection time of each group of point cloud data, the infrared images and point cloud data whose collection time difference is less than or equal to a preset threshold value can be determined as the infrared images and point cloud data collected simultaneously.

[0065] The disclosed embodiment acquires the infrared image and point cloud data of the contact network collected by the monitoring terminal. The two hanging holes arranged on the monitoring terminal are respectively hung and fixed on the flat arm and the inclined arm of the contact network support. The infrared image and the point cloud data are processed in time synchronization to obtain the infrared image and the point cloud data of the contact network collected simultaneously, which can further improve the accuracy of the data when the target ice thickness is determined by multivariate data fusion.

[0066] In some embodiments of the present disclosure, the contact network ice-melting device can input an infrared image into a pre-trained image recognition model to obtain a first ice thickness of the contact network output by the image recognition model, wherein the image recognition model is obtained by training a convolutional neural network based on pre-collected infrared images of contact network ice and corresponding ice thickness labels.

[0067] Specifically, the convolutional neural network can be MobileNetV3, and the pre-collected infrared images of the contact network ice can include infrared image samples of different ice thicknesses, which cover various conditions that may be encountered in the expected use scenario, and each infrared image of the contact network ice corresponds to an ice thickness label. Among them, the pre-collected infrared images of the contact network ice and the corresponding ice thickness labels can be divided into a training set, a validation set, and a test set. In the model training process, the pre-trained MobileNetV3 model can be used as a starting point to speed up the training speed and improve the initial performance of the model. The loss function can be a mean square error loss function. The model is optimized using an adaptive moment estimation (Adaptive Moment Estimation, Adam) optimizer, and the learning rate and other hyperparameters are set for it. The learning rate decay strategy is implemented, and an iterative training method is adopted. After each iteration, an evaluation is performed on the validation set to monitor the model performance, and the model training is determined to be completed after the model performance meets the preset requirements, and the image recognition model is obtained.

[0068] After the image recognition model is trained, the contact network de-icing device can input the collected infrared image of the contact network into the pre-trained image recognition model, and the image recognition model will recognize and analyze the infrared image and output the first ice thickness of the contact network.

[0069] Figure 5 is a flow chart of a method for determining a second ice thickness provided by an embodiment of the present disclosure, such as Figure 5 As shown, based on the above embodiment, the second ice coating thickness can be determined by the following method.

[0070] S501, extracting feature points from point cloud data, and constructing a three-dimensional model of the contact network based on the extracted target feature points.

[0071] In the disclosed embodiment, the contact network ice-melting device can identify and extract feature points of the point cloud data after acquiring the point cloud data of the contact network, and determine target feature points such as the conductors and load-bearing cables of the contact network.

[0072] In an exemplary implementation of the disclosed embodiment, the contact network de-icing device may first pre-process the point cloud data to remove noise points in the point cloud data, and then use a filtering algorithm (such as Gaussian filtering, bilateral filtering, etc.) to smooth the point cloud data, and then determine the area with significant change characteristics in the point cloud according to the shape distribution of the point cloud, such as the intersection of the conductor and the load-bearing cable, the special deformation point on the conductor, etc., and determine it as the target feature point, and then use a multi-scale adaptive feature classification algorithm to classify the extracted target feature points, distinguish different types of target feature points such as conductors and load-bearing cables, and combine with a clustering algorithm (such as density-based spatial clustering of applications with noise, DBSCAN) to cluster the target feature points into different clusters, each cluster represents a contact network component (such as a conductor, a load-bearing cable), and establish a three-dimensional model of the contact network in an un-iced state according to the size parameters of the contact network components obtained in advance, and then align the three-dimensional model with the point cloud data according to the spatial position of the target feature points in the clustering results and the corresponding component type.

[0073] S502: Compare the point cloud data with the three-dimensional model to determine an ice-covered area in the point cloud data, and determine a second ice-covered thickness of the contact network based on the ice-covered area.

[0074] In the disclosed embodiment, the contact network de-icing device can, after successfully constructing a three-dimensional model of the contact network in an un-iced state, compare the point cloud data with the three-dimensional model to determine the ice-covered area in the point cloud data. Specifically, the area where the difference between the point cloud data and the three-dimensional model is large can be determined as the ice-covered area, and the second ice thickness of the contact network can be determined based on the ice-covered area. Specifically, the average vertical distance between the point cloud data and the three-dimensional model can be calculated in the ice-covered area and determined as the second ice thickness of the contact network.

[0075] The disclosed embodiment extracts feature points from point cloud data, builds a three-dimensional model of the contact network based on the extracted target feature points, compares the point cloud data with the three-dimensional model, determines the ice-covered area in the point cloud data, and determines the second ice-covered thickness of the contact network based on the ice-covered area. The three-dimensional model of the contact network can be established, and the ice-covered area can be identified. Furthermore, the point cloud data and the three-dimensional model can be compared within the ice-covered area to improve the accuracy of determining the second ice-covered thickness.

[0076] Figure 6is a flow chart of a method for performing ice melting operation provided by an embodiment of the present disclosure, such as Figure 6 As shown, based on the above embodiment, the ice melting operation can be performed by the following method.

[0077] S601. Determine initial ice melting parameters based on a target ice coating thickness, and send the initial ice melting parameters to a control device, so that the control device performs an overhead line ice melting operation based on the initial ice melting parameters.

[0078] In the embodiment of the present disclosure, the contact network ice-melting device can determine the initial ice-melting parameters according to the target ice-melting thickness after determining the target ice-melting thickness, and send the initial ice-melting parameters to the control device, so that the control device performs the contact network ice-melting operation based on the initial ice-melting parameters, wherein the method for determining the initial ice-melting parameters is similar to S105 and will not be repeated here.

[0079] S602. When the execution time of the contact network de-icing operation performed by the control device based on the initial de-icing parameters reaches a preset time, obtain the current environmental parameters, the current ice thickness and de-icing result parameters, where the de-icing result parameters include at least one of de-icing efficiency and power consumption.

[0080] The environmental parameters in the disclosed embodiments may include at least one of the ambient temperature, ambient humidity, and ambient wind speed. The current ice thickness may be understood as the ice thickness determined by the fusion of the infrared image and point cloud data of the contact network collected at the current moment. The ice melting efficiency may be understood as the weight or volume of ice melted within a preset time or per unit time. The power consumption may be understood as the power consumed for melting ice within a preset time.

[0081] In the disclosed embodiment, the contact network ice-melting device can record the execution time of the contact network ice-melting operation after the control device starts to execute the contact network ice-melting operation based on the initial ice-melting parameters, and when the execution time reaches the preset time, obtain the environmental parameters at the current moment collected by the environmental sensor, the current ice thickness determined according to the infrared image and point cloud data collected at the current moment, the ice melting efficiency determined according to the current ice thickness, and the electric energy consumption measured by the electric meter.

[0082] S603: Determine target ice-melting parameters based on the current environmental parameters, the current ice thickness and the ice-melting result parameters, and send the target ice-melting parameters to the control device so that the control device performs the contact network ice-melting operation based on the target ice-melting parameters.

[0083] In the disclosed embodiment, after obtaining the environmental parameters, current ice thickness and ice melting result parameters at the current moment, the contact network ice melting device can use an adaptive learning algorithm to adjust the initial ice melting parameters to obtain the optimized target ice melting parameters, and send the target ice melting parameters to the control device, so that the control device performs the contact network ice melting operation based on the target ice melting parameters. When the execution time of the control device performing the contact network ice melting operation based on the target ice melting parameters reaches the preset time again, the environmental parameters, current ice thickness and ice melting result parameters at the current moment are obtained, and based on the newly determined environmental parameters, current ice thickness and ice melting result parameters at the current moment, new target ice melting parameters are determined, and the new target ice melting parameters are sent to the control device, so that the control device performs the contact network ice melting operation based on the new target ice melting parameters, and so on, until the ice melting is completed. Among them, the preset time can be set according to the needs.

[0084] In an exemplary implementation of the disclosed embodiment, the contact network de-icing device can input the current environmental parameters, the current ice thickness and the de-icing result parameters into a pre-trained parameter optimization model to obtain the target de-icing parameters output by the parameter optimization model, wherein the parameter optimization model is obtained by training a support vector machine based on pre-collected historical de-icing data.

[0085] Specifically, the contact network ice-melting device can train the support vector machine based on the historical ice-melting data collected in advance. The historical ice-melting data can include the ice-melting result parameters (including ice-melting efficiency and electric energy consumption) within a preset time after the start of ice-melting in the historical ice-melting process, the environmental parameters after the preset time, the ice thickness, and the optimized ice-melting parameters adopted after the preset time, wherein the optimized ice-melting parameters are used as training labels. In the model training process, the ice-melting time in the optimized ice-melting parameters can be used as the first optimization target, and the electric energy consumption can be used as the second optimization target. Specifically, different weights can be set for the ice-melting time and the electric energy consumption, and the weighted sum of the two is calculated, and the weighted sum is used as an evaluation index. According to the evaluation index, the historical ice-melting data is screened, and the historical ice-melting data with a weighted sum greater than or equal to the preset threshold is used as the actual training data. The ice-melting result parameters within the preset time, the environmental parameters after the preset time, and the ice thickness in the screened historical ice-melting data are input into the support vector machine for parameter optimization prediction. The ice-melting parameters output by the support vector machine are compared with the optimized ice-melting parameters in the historical ice-melting data, and the loss function (such as the mean square error loss function) is calculated. The model parameters are optimized by a genetic algorithm or a particle swarm optimization algorithm based on the loss function. The electric energy consumption is calculated according to the ice-melting parameters output by the model, and then the evaluation index is calculated according to the electric energy consumption and the ice-melting time in the ice-melting parameters. If the evaluation index meets the preset conditions, it is determined that the parameter optimization model training is completed. Otherwise, the hyperparameters of the model are further adjusted based on the evaluation index so that the evaluation index corresponding to the output data of the adjusted parameter optimization model meets the preset conditions.

[0086] The disclosed embodiment determines initial ice-melting parameters based on target ice-covering thickness, and sends the initial ice-melting parameters to a control device, so that the control device performs contact network ice-melting operations based on the initial ice-melting parameters. When the execution time of the control device performing the contact network ice-melting operations based on the initial ice-melting parameters reaches a preset time, the current environmental parameters, the current ice-covering thickness and ice-melting result parameters are obtained, and the ice-melting result parameters include at least one of ice-melting efficiency and electric energy consumption. Based on the current environmental parameters, the current ice-covering thickness and ice-melting result parameters, target ice-melting parameters are determined, and the target ice-melting parameters are sent to the control device, so that the control device performs contact network ice-melting operations based on the target ice-melting parameters. The control device can learn from historical data and current data, and pay attention to the static characteristics and dynamic change trends of ice-melting data, so as to dynamically adjust and optimize the ice-melting strategy, shorten the ice-melting time as much as possible, reduce the ice-melting cost, and improve the ice-melting effect and resource utilization efficiency.

[0087] Figure 7 Schematic diagram of the structure of a contact network ice melting device provided by the embodiment of the present disclosure. Figure 7As shown, the contact network ice-melting device 700 includes: an acquisition module 710, an image recognition module 720, a point cloud analysis module 730, a thickness determination module 740, and a parameter determination module 750, wherein the acquisition module 710 is used to acquire the infrared image and point cloud data of the contact network collected simultaneously; the image recognition module 720 is used to perform image recognition on the infrared image to determine the first ice coating thickness of the contact network; the point cloud analysis module 730 is used to analyze the point cloud data to determine the second ice coating thickness of the contact network; the thickness determination module 740 is used to fuse the first ice coating thickness with the second ice coating thickness to determine the target ice coating thickness of the contact network; the parameter determination module 750 is used to determine the ice melting parameters based on the target ice coating thickness, and send the ice melting parameters to the control device, so that the control device performs the contact network ice melting operation based on the ice melting parameters.

[0088] Optionally, the acquisition module 710 includes: a first acquisition unit, used to acquire the infrared image and point cloud data of the contact network collected by the monitoring terminal, and the two hanging holes set on the monitoring terminal are respectively hung and fixed on the flat arm and the inclined arm of the contact network support; a time synchronization unit, used to perform time synchronization processing on the infrared image and point cloud data to obtain the infrared image and point cloud data of the contact network collected simultaneously.

[0089] Optionally, the image recognition module 720 is specifically used to input the infrared image into a pre-trained image recognition model to obtain a first ice thickness of the contact network output by the image recognition model, wherein the image recognition model is obtained by training a convolutional neural network based on pre-collected contact network ice infrared images and corresponding ice thickness labels.

[0090] Optionally, the point cloud analysis module 730 includes: an extraction unit, used to extract feature points from the point cloud data, and construct a three-dimensional model of the contact network based on the extracted target feature points; a comparison unit, used to compare the point cloud data with the three-dimensional model, determine the ice-covered area in the point cloud data, and determine the second ice-covered thickness of the contact network based on the ice-covered area.

[0091] Optionally, the parameter determination module 750 includes: a first determination unit, used to determine initial ice melting parameters based on the target ice thickness, and send the initial ice melting parameters to the control device, so that the control device performs the contact network ice melting operation based on the initial ice melting parameters; a second acquisition unit, used to obtain the current environmental parameters, current ice thickness and ice melting result parameters when the execution time of the contact network ice melting operation performed by the control device based on the initial ice melting parameters reaches a preset time, the ice melting result parameters including at least one of ice melting efficiency and electric energy consumption; the second determination unit, used to determine the target ice melting parameters based on the current environmental parameters, the current ice thickness and the ice melting result parameters, and send the target ice melting parameters to the control device, so that the control device performs the contact network ice melting operation based on the target ice melting parameters.

[0092] Optionally, the second determination unit is specifically used to input the environmental parameters at the current moment, the current ice cover thickness and the ice melting result parameters into a pre-trained parameter optimization model to obtain the target ice melting parameters output by the parameter optimization model, wherein the parameter optimization model is obtained by training a support vector machine based on pre-collected historical ice melting data.

[0093] The contact network ice-melting device provided in this embodiment can execute the method described in any of the above embodiments, and its execution method and beneficial effects are similar, which will not be repeated here.

[0094] Figure 8 It is a structural diagram of a computer device provided in an embodiment of the present disclosure.

[0095] like Figure 8 As shown, the computer device may include a processor 810 and a memory 820 storing computer program instructions.

[0096] Specifically, the processor 810 may include a central processing unit (CPU), or an application specific integrated circuit (ASIC), or may be configured to implement one or more integrated circuits of the embodiments of the present application.

[0097] The memory 820 may include a large capacity memory for information or instructions. By way of example and not limitation, the memory 820 may include a hard disk drive (HDD), a floppy disk drive, a flash memory, an optical disk, a magneto-optical disk, a tape, or a universal serial bus (USB) drive or a combination of two or more of these. Where appropriate, the memory 820 may include a removable or non-removable (or fixed) medium. Where appropriate, the memory 820 may be inside or outside the integrated gateway device. In a particular embodiment, the memory 820 is a non-volatile solid-state memory. In a particular embodiment, the memory 820 includes a read-only memory (ROM). Where appropriate, the ROM may be a mask-programmed ROM, a programmable ROM (PROM), an erasable PROM (EPROM), an electrically erasable PROM (Electrically Erasable Programmable ROM, EEPROM), an electrically rewritable ROM (EAROM) or a flash memory, or a combination of two or more of these.

[0098] The processor 810 reads and executes the computer program instructions stored in the memory 820 to perform the steps of the contact network ice melting method provided in the embodiment of the present disclosure.

[0099] In one example, the computer device may further include a transceiver 830 and a bus 840. Figure 8 As shown, the processor 810, the memory 820 and the transceiver 830 are connected via a bus 840 and communicate with each other.

[0100] The bus 840 includes hardware, software, or both. For example, but not limitation, the bus may include an Accelerated Graphics Port (AGP) or other graphics bus, an Extended Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), a Hyper Transport (HT) interconnect, an Industrial Standard Architecture (ISA) bus, an InfiniBand interconnect, a Low Pin Count (LPC) bus, a memory bus, a MicroChannel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a Video Electronics Standards Association Local Bus (VLB) bus, or other suitable buses or a combination of two or more of these. Where appropriate, the bus 840 may include one or more buses. Although embodiments of the present application describe and illustrate a particular bus, the present application contemplates any suitable bus or interconnect.

[0101] The embodiments of the present disclosure also provide a computer-readable storage medium, which may store a computer program. When the computer program is executed by a processor, the processor implements the contact network ice melting method provided by the embodiments of the present disclosure.

[0102] The embodiments of the present disclosure also provide a computer program product, including a computer program. When the computer program is executed by a processor, the processor implements the contact network ice melting method provided by the embodiments of the present disclosure.

[0103] The above-mentioned storage medium may, for example, include a memory 820 of computer program instructions, and the above-mentioned instructions may be executed by the processor 810 of the contact network de-icing device to complete the contact network de-icing method provided by the embodiment of the present disclosure. Optionally, the storage medium may be a non-temporary computer-readable storage medium, for example, the non-temporary computer-readable storage medium may be a ROM, a random access memory (Random Access Memory, RAM), a compact disc read-only memory (Compact Disc ROM, CD-ROM), a magnetic tape, a floppy disk, and an optical data storage device, etc. The above-mentioned computer program may be written in any combination of one or more programming languages ​​to perform the program code of the operation of the embodiment of the present disclosure, and the programming language includes an object-oriented programming language, such as Java, C++, etc., and also includes a conventional procedural programming language, such as "C" language or a similar programming language. The program code may be executed entirely on the user computing device, partially on the user device, as an independent software package, partially on the user computing device and partially on the remote computing device, or completely on the remote computing device or server.

[0104] It should be noted that, in this article, relational terms such as "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0105] The above description is only a specific embodiment of the present disclosure, so that those skilled in the art can understand or implement the present disclosure. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present disclosure. Therefore, the present disclosure will not be limited to the embodiments described herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A contact network de-icing method, characterized in that: The method comprises: Acquire infrared images and point cloud data of the contact network collected simultaneously; Performing image recognition on the infrared image to determine a first ice coating thickness of the contact network; Analyzing the point cloud data to determine a second ice coating thickness of the contact network; The first ice coating thickness and the second ice coating thickness are combined to determine a target ice coating thickness of the contact network; Determine ice melting parameters based on the target ice coating thickness, and send the ice melting parameters to a control device so that the control device performs an overhead line ice melting operation based on the ice melting parameters.

2. The method according to claim 1, characterized in that The step of acquiring the infrared image and point cloud data of the contact network collected simultaneously includes: Acquire infrared images and point cloud data of the contact network collected by the monitoring terminal, wherein two hanging holes provided on the monitoring terminal are respectively hung and fixed on the flat arm and the oblique arm of the contact network support; The infrared image and point cloud data are subjected to time synchronization processing to obtain infrared images and point cloud data of the contact network collected simultaneously.

3. The method according to claim 1, characterized in that The performing image recognition on the infrared image to determine the first ice thickness of the contact network includes: The infrared image is input into a pre-trained image recognition model to obtain a first ice thickness of the contact network output by the image recognition model, wherein the image recognition model is obtained by training a convolutional neural network based on pre-collected infrared images of ice coverage on the contact network and corresponding ice thickness labels.

4. The method according to claim 1, characterized in that The step of analyzing the point cloud data to determine the second ice thickness of the contact network includes: Extracting feature points from the point cloud data, and constructing a three-dimensional model of the contact network based on the extracted target feature points; The point cloud data is compared with the three-dimensional model to determine an ice-covered area in the point cloud data, and a second ice-covered thickness of the contact network is determined based on the ice-covered area.

5. The method according to claim 1, characterized in that The step of determining ice melting parameters based on the target ice thickness and sending the ice melting parameters to a control device so that the control device performs an overhead line ice melting operation based on the ice melting parameters includes: Determining initial ice melting parameters based on the target ice thickness, and sending the initial ice melting parameters to the control device, so that the control device performs overhead line ice melting operations based on the initial ice melting parameters; When the execution time of the contact network de-icing operation performed by the control device based on the initial de-icing parameters reaches a preset time, the current environmental parameters, the current ice thickness and de-icing result parameters are obtained, and the de-icing result parameters include at least one of de-icing efficiency and electric energy consumption; Based on the environmental parameters at the current moment, the current ice thickness and the ice melting result parameters, target ice melting parameters are determined, and the target ice melting parameters are sent to the control device so that the control device performs the contact network ice melting operation based on the target ice melting parameters.

6. The method according to claim 5, characterized in that The determining of target ice melting parameters based on the environmental parameters at the current moment, the current ice thickness and the ice melting result parameters includes: The environmental parameters at the current moment, the current ice thickness and the ice melting result parameters are input into a pre-trained parameter optimization model to obtain the target ice melting parameters output by the parameter optimization model, wherein the parameter optimization model is obtained by training a support vector machine based on pre-collected historical ice melting data.

7. A contact network ice melting device, characterized in that: include: An acquisition module, used to acquire infrared images and point cloud data of the contact network collected simultaneously; An image recognition module, used for performing image recognition on the infrared image to determine a first ice thickness of the contact network; A point cloud analysis module, used for analyzing the point cloud data to determine a second ice thickness of the contact network; a thickness determination module, configured to fuse the first ice coating thickness and the second ice coating thickness to determine a target ice coating thickness of the contact network; The parameter determination module is used to determine ice melting parameters based on the target ice coating thickness, and send the ice melting parameters to the control device, so that the control device performs the contact network ice melting operation based on the ice melting parameters.

8. A computer device, characterized in that: include: Memory; processor; and a computer program; wherein the computer program is stored in the memory and is configured to be executed by the processor to implement the contact network ice melting method according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that: The storage medium stores a computer program, and when the computer program is executed by a processor, the contact network de-icing method according to any one of claims 1 to 6 is implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the contact network ice melting method according to any one of claims 1 to 6 is implemented.

Images